Bus shelter based on intelligent network connection technology application

Abstract

The invention discloses a bus shelter based on intelligent network connection technology application. The correlation degree between a bus and a bus shelter in the prior art is not high, and the prediction result of the arrival time of the bus is not accurate. According to the invention, the Gaussian plume model is utilized to simulate the driving process of the road vehicle between every two intersections, the influence of the road traffic flow on the arrival time of the bus is accurately analyzed, the real-time bus information is provided, and the real-time bus information is provided through direct communication and exchange with short-distance vehicles. Compared with traditional positioning information station reporting, more accurate station entering and exiting information issuing can be provided. Information interaction between passengers and the public transportation system is realized, and travel experience is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of public transportation intelligent facilities and relates to a bus shelter based on the application of intelligent network connection technology. Background Art

[0002] Traditional bus shelters have relatively simple functions, only providing basic wind and rain protection, which is difficult to meet the needs of modern urban public transportation systems for informatization and intelligence. Modern smart bus shelters mainly meet the functions of intelligent integration and information services such as bus forecast station information release, multimedia information release, passenger convenience services, video surveillance, etc., which basically meet the application requirements of current public transportation systems.

[0003] However, with the development of intelligent network technology, the prospect of driverless vehicles is getting closer and closer. In order to timely integrate smart bus stops into future connected system services such as people, vehicles, roads and clouds, it is necessary to further effectively connect buses and bus shelters through the network to provide richer information and services, improve passengers' travel experience and the efficiency of the public transportation system. Summary of the invention

[0004] In order to solve the problems existing in the background technology, the present invention proposes a bus shelter based on the application of intelligent network connection technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0006] The data acquisition module collects images of vehicles entering the bus travel area based on time series;

[0007] The data processing module identifies vehicle features, marks vehicles, predicts the fuzzy position of vehicles, and updates the traffic flow in the bus travel interval in real time when the vehicle exits the bus travel interval;

[0008] The bus timing module predicts the arrival time of the bus according to the traffic volume within the bus travel range;

[0009] Information display module, showing the time required for the bus to arrive at the current station, providing intuitive information for passengers;

[0010] The data transmission module coordinates and schedules the sending and receiving of information between various modules.

[0011] Furthermore, the data acquisition module collects images of vehicles entering the bus travel interval according to the time series;

[0012] The data processing module identifies vehicle features and marks the vehicle;

[0013] The data processing module predicts the fuzzy position of the bus within the travel range based on time and space factors;

[0014] The data processing module determines the traffic volume in the bus driving interval according to the time when the vehicle enters and exits the bus driving interval;

[0015] The bus timing module simulates the driving process of road vehicles based on the Gaussian smoke plume model and calculates the arrival time of buses;

[0016] The information display module displays the time required for the bus to arrive at the current stop.

[0017] Furthermore, the data processing module identifies vehicle features and marks the vehicle in a specific manner as follows:

[0018] Perform edge detection on the vehicle images collected by the data acquisition module and detect the corresponding position of the license plate;

[0019] Extract the corresponding position of the license plate and segment the area where the license plate is located according to a fixed ratio;

[0020] Compare the segmented license plate area with the existing character shape to obtain the vehicle license plate number mark;

[0021] Extract the nature of the vehicle and related vehicle operating status and positioning information based on the license plate number mark.

[0022] Furthermore, the data processing module predicts the fuzzy position of the vehicle within the bus driving range, and uses the vehicle image acquisition time and acquisition space location in the historical time to calculate the speed change and vehicle turning of different bus driving ranges;

[0023] The first deep learning model is used to predict the fuzzy position of any vehicle based on the vehicle speed and vehicle turning in the historical time data. In the prediction result, multiple position points are generated based on multiple turning opportunities.

[0024] Set the time it takes for a vehicle to reach the bus stop corresponding to a turning opportunity at the predicted speed. If the vehicle does not pass the bus stop corresponding to the turning opportunity after this time, the predicted point will be deleted.

[0025] Furthermore, the bus timing module predicts the bus arrival time by:

[0026] A Gaussian plume model is established on the current bus route to simulate the traffic flow from the current intersection to the next nearest intersection of the current intersection. The specific formula is:

[0027]

[0028] Where (x, y) is the position of the next intersection, C(x, y) is the traffic volume of the next intersection, Q is the traffic volume of the current intersection, u is the average speed of the vehicle, x0, y0 is the position of the current intersection, σ x is the standard deviation of the diffusion of vehicles on the road in the direction of travel, σ y is the standard deviation of the diffusion of vehicles on the road in the direction perpendicular to the lane, σ x The value of is equal to the distance from the current intersection to the next nearest intersection, σ y The value of is equal to the number of lanes on the current road;

[0029] Based on the traffic light of the next nearest intersection to the current intersection, if the light is green, the Gaussian smoke plume model diffuses normally;

[0030] If the traffic light at the next nearest intersection of the current intersection is red, a restriction condition is added to stop the vehicles that have diffused to the next nearest intersection of the current intersection in the Gaussian smoke plume model from diffusing and stack them to the next nearest intersection of the current intersection;

[0031] Substitute the current bus position into the Gaussian plume model and record the time required for the current bus to diffuse to the destination.

[0032] Furthermore, the data transmission module transmits data using the V2X communication mode.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] Providing real-time bus information, through direct communication and exchange with nearby vehicles, it can provide more accurate entry and exit information release compared to traditional positioning information announcements. It realizes information interaction between passengers and the bus system and improves the travel experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a system module architecture diagram of the present invention;

[0036] Figure 2 It is a flow chart of the operation of the system of the present invention;

[0037] Figure 3 It is a system module collaboration diagram of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] The technical solution adopted by the present invention is as follows.

[0041] like Figure 1 As shown, a bus shelter based on the application of intelligent network connection technology includes:

[0042] The data acquisition module obtains road information in real time based on vehicle networking technology, including collecting images of vehicles entering the bus driving range, the number of vehicles, and road traffic light information based on time series.

[0043] The data processing module identifies vehicle features, marks vehicles, predicts the fuzzy position of vehicles, and updates the traffic flow in the bus travel interval in real time when the vehicle exits the bus travel interval;

[0044] The bus timing module predicts the arrival time of the bus according to the traffic volume within the bus travel range;

[0045] Information display module, showing the time required for the bus to arrive at the current station, providing intuitive information for passengers;

[0046] The data transmission module coordinates and schedules the sending and receiving of information between various modules.

[0047] like Figure 2 As shown, the method performed by the bus shelter based on the application of intelligent network connection technology includes:

[0048] The data acquisition module collects images of vehicles entering the bus travel range based on time series;

[0049] The data processing module identifies vehicle features and marks the vehicle;

[0050] The data processing module predicts the fuzzy position of the bus within the travel range based on time and space factors;

[0051] The data processing module determines the traffic volume in the bus driving interval according to the time when the vehicle enters and exits the bus driving interval;

[0052] The bus timing module simulates the driving process of road vehicles based on the Gaussian smoke plume model and calculates the arrival time of buses;

[0053] The information display module displays the time required for the bus to arrive at the current stop.

[0054] First, we collect vehicle images that enter the bus travel range according to the time series, identify the vehicle features in the collected vehicle images, and uniquely mark the vehicle. In this solution, we extract the vehicle license plate number, which can ensure the uniqueness of the vehicle and will not be blocked, so that the unique mark of the vehicle can be completely extracted.

[0055] Perform edge detection on the vehicle images collected by the data acquisition module to detect the corresponding position of the license plate. Edge detection can be performed in many ways, such as canny operator, gradient value extraction, expansion and corrosion, and the edge of the vehicle can be extracted by any method.

[0056] The corresponding position of the license plate is extracted, and the area where the license plate is located is segmented according to a fixed ratio. The corresponding position of the license plate can be extracted by a deep learning model, a convolutional neural network or a feature classifier. After the corresponding position of the license plate is extracted, according to a fixed ratio, a single character on the license plate is 45mm wide, and the space of a single character includes the space on the left and right. The stroke width of the character is 10mm, and the gap between the second and third characters from left to right is 34mm, and the gap between other characters is 12mm. The total number of characters is 7 and the width of a single character accounts for about 10% of the width of the license plate. The character area in the license plate is segmented by a fixed ratio.

[0057] The segmented license plate area is compared with the existing character shape to obtain the vehicle's license plate number mark.

[0058] After obtaining the vehicle's license plate number, the network query is performed based on the network connection technology to extract the nature of the vehicle and related vehicle operation status and positioning information. When a vehicle passes through multiple bus shelters, the information of the same vehicle can be analyzed through multiple bus shelters to obtain information such as the vehicle's operation status.

[0059] The data processing module predicts the fuzzy position of the vehicle within the bus driving range based on time and space factors. The speed change and vehicle turning situation in different bus driving ranges are calculated by using the vehicle image collection time and collection space location in the historical time.

[0060] Set the time it takes for a vehicle to reach the bus stop corresponding to a turning opportunity at the predicted speed. If the vehicle does not pass the bus stop corresponding to the turning opportunity after this time, the predicted point will be deleted.

[0061] In historical time, the vehicle image collection time and collection space location should appear in groups. For example, vehicle A enters the first bus driving section. Vehicle A may not drive out of the first bus driving section, but turns into the second bus driving section. At this time, vehicle A is collected in the second bus driving section, indicating that vehicle A has left the first bus driving section.

[0062] The first deep learning model is used to predict the fuzzy position of any vehicle based on the vehicle speed and vehicle turning in the historical time data. This includes predicting the vehicle speed and the probability of the vehicle turning during driving. In the prediction results, multiple location points are generated based on multiple turning opportunities. During the driving process of the vehicle, the turning record of the vehicle is not a fixed factor. At this time, multiple prediction results need to be generated until the vehicle leaves the bus driving range.

[0063] The bus arrival time is simulated based on the traffic flow factor, and a Gaussian smoke plume model is established on the current bus route to simulate the traffic flow from the current intersection to the next nearest intersection of the current intersection. The specific formula is:

[0064]

[0065] Where (x, y) is the position of the next intersection, C(x, y) is the traffic volume of the next intersection, Q is the traffic volume of the current intersection, u is the average speed of the vehicle, x0, y0 is the position of the current intersection, σ x is the standard deviation of the diffusion of vehicles on the road in the direction of travel, σ y is the standard deviation of the diffusion of vehicles on the road in the direction perpendicular to the lane, σ x The value of is equal to the distance from the current intersection to the next nearest intersection, σ y The value of is equal to the number of lanes on the current road.

[0066] Based on the traffic light at the next nearest intersection to the current intersection, if the light is green, the Gaussian smoke plume model diffuses normally.

[0067] If the traffic light at the next nearest intersection of the current intersection is red, a restriction condition is added to stop the vehicles that have diffused to the next nearest intersection of the current intersection in the Gaussian smoke plume model from diffusing and stack them to the next nearest intersection position of the current intersection.

[0068] Substitute the current bus position into the Gaussian plume model and record the time required for the current bus to diffuse to the destination.

[0069] The Gaussian plume model was originally an algorithm for simulating the propagation of pollutants in the air. Based on the orderliness and directionality of vehicle travel on the road, it can regard intersections on the road as pollution sources. Based on the actual road conditions, the Gaussian plume model is modified and traffic light restrictions are added at intersections, which can effectively simulate the position of vehicles on the road.

[0070] In order to verify the practicability of the present invention, an experimental verification was carried out on the same bus from the monitored intersection to the designated bus stop under different traffic flow conditions, as shown in the following table.

[0071]

[0072]

[0073] Based on the above simulation results, it can be seen that the calculation result of the bus arrival time by the Gaussian plume model is obviously linearly correlated with the traffic volume, which conforms to the objective law, and the simulation result of the bus arrival time conforms to the objective situation. Therefore, by simulating the road traffic flow and extracting the bus points in the traffic flow through the Gaussian plume model, it can meet the requirements of high-precision prediction of bus arrival time.

[0074] In the above method, data transmission uses the V2X communication mode to transmit data. V2X includes various application communication scenarios such as vehicle-to-vehicle V2V (Vehicle-to-Vehicle), vehicle-to-infrastructure V2I, vehicle-to-pedestrian V2P, and vehicle-to-external network V2N. In the bus shelters where intelligent network technology is applied, the data sharing efficiency of V2X can be maximized.

[0075] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A bus shelter based on the application of intelligent network technology, characterized in that: The following methods are included: Data acquisition module, which obtains road information in real time based on vehicle networking technology; The data processing module identifies vehicle features, marks vehicles, predicts the fuzzy position of vehicles, and updates the traffic flow in the bus travel interval in real time when the vehicle exits the bus travel interval; The bus timing module predicts the arrival time of the bus according to the traffic volume within the bus travel range; Information display module, showing the time required for the bus to arrive at the current station, providing intuitive information for passengers; The data transmission module coordinates and schedules the sending and receiving of information between various modules.

2. A bus shelter based on the application of intelligent network connection technology according to claim 1, characterized in that: The data acquisition module collects images of vehicles entering the bus travel range based on time series; The data processing module identifies vehicle features and marks the vehicle; The data processing module predicts the fuzzy position of the bus within the travel range based on time and space factors; The data processing module determines the traffic volume in the bus driving interval according to the time when the vehicle enters and exits the bus driving interval; The bus timing module simulates the driving process of road vehicles based on the Gaussian smoke plume model and calculates the arrival time of buses; The information display module displays the time required for the bus to arrive at the current stop.

3. The bus shelter based on the application of intelligent network connection technology according to claim 1 is characterized in that: The specific method of the data processing module identifying vehicle features and marking the vehicle is as follows: Perform edge detection on the vehicle images collected by the data acquisition module and detect the corresponding position of the license plate; Extract the corresponding position of the license plate and segment the area where the license plate is located according to a fixed ratio; Compare the segmented license plate area with the existing character shape to obtain the vehicle license plate number mark; Extract the nature of the vehicle and related vehicle operating status and positioning information based on the license plate number mark.

4. The bus shelter based on the application of intelligent network connection technology according to claim 1, characterized in that: The data processing module predicts the fuzzy position of the vehicle within the bus driving range, and uses the vehicle image collection time and collection space location in the historical time to calculate the speed change and vehicle turning of different bus driving ranges; The first deep learning model is used to predict the fuzzy position of any vehicle based on the vehicle speed and vehicle turning in the historical time data. In the prediction result, multiple position points are generated based on multiple turning opportunities. And the vehicle is in a certain predicted turning position, Set the time it takes for a vehicle to reach the bus stop corresponding to a turning opportunity at the predicted speed. If the vehicle does not pass the bus stop corresponding to the turning opportunity after this time, the predicted point will be deleted.

5. The bus shelter based on the application of intelligent network connection technology according to claim 1, characterized in that: The method used by the bus timing module to predict the arrival time of buses is: A Gaussian plume model is established on the current bus route to simulate the traffic flow from the current intersection to the next nearest intersection of the current intersection. The specific formula is: Where (x, y) is the position of the next intersection, C(x, y) is the traffic volume of the next intersection, Q is the traffic volume of the current intersection, u is the average speed of the vehicle, x0, y0 is the position of the current intersection, σ x is the standard deviation of the diffusion of vehicles on the road in the direction of travel, σ y is the standard deviation of the diffusion of vehicles on the road in the direction perpendicular to the lane, σ x The value of is equal to the distance from the current intersection to the next nearest intersection, σ y The value of is equal to the number of lanes on the current road; Based on the traffic light of the next nearest intersection to the current intersection, if the light is green, the Gaussian smoke plume model diffuses normally; If the traffic light at the next nearest intersection of the current intersection is red, a restriction condition is added to stop the vehicles that have diffused to the next nearest intersection of the current intersection in the Gaussian smoke plume model from diffusing and stack them to the next nearest intersection of the current intersection; Substitute the current bus position into the Gaussian plume model and record the time required for the current bus to diffuse to the destination.

6. The bus shelter based on the application of intelligent network connection technology according to claim 1, characterized in that: The data transmission module transmits data using the V2X communication mode.

Images